Skip to content

Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration.

Yang Zhao, Yangou Ouyang, Xiao Ding, Hepeng Wang, Bibo Cai, Kai Xiong, Jinglong Gao, Zhouhao Sun, Li Du, Bing Qin, Ting Liu

VenueA*ACL
Year2026
ProceedingsACL (1)

Browse the full ACL paper archive.